Multimodal machine translation through visuals and speech

Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space.

Social Applications of Speech-Translation Technology

Automatic spoken language translation has finally entered widespread use. Still emerging, however, are speech-translation systems directed at various demanding and socially significant use cases. Because speech-recognition and -translation technologies remain error-prone, speech-translation output is often below the threshold of usability when accuracy is essential; and present use is still largely restricted to areas like social networking or travel in which no representation concerning accuracy is demanded. This chapter, while recognizing the importance of continued improvements in speech-recognition and -translation accuracy per se, aims to support the conviction that the path toward widespread use of socially substantial spoken language translation can be shortened by emphasizing reliability (accountability and user confidence) and customization (tight adaptation for the targeted use case). Examined here are several socially significant speech-translation systems which aim to meet those requirements, with focus upon current systems in (1) healthcare and (2) presentations for education, academic conferences, and government.